Minaco

Qwen4-Max

Qwen4-Max is Alibaba’s flagship Qwen4 model for long-context reasoning, coding, professional work and tool-using agent tasks.

When to try it.

Try a long-running repository or professional workflow that benefits from a large context window and explicit tool use.

What to weigh

Published benchmark results are from the Qwen Team, not independent Minaco tests. Minaco publishes Qwen4-Max for Qwen Code and Hermes Agent.

A first task

Review this multi-stage project, preserve the accepted constraints and complete the next verifiable step.

This is a suggested evaluation task. Check the result against your own requirements; it is not a benchmark or a guarantee of performance.

Know the rate.

Currently published for Qwen Code. Rates below are Minaco Credits per one million tokens.

Input
3,000
Cached input
150
Output
9,000

Cache writes: 3,750 Credits per million tokens.

Estimate a model call

Example: 10,000 uncached input tokens and 1,000 output tokens cost approximately 39 Credits before per-request rounding.

An agent turn may make several model calls. Context, tool results and billable reasoning tokens affect the total; enter cache-write tokens separately when applicable. The prompt total determines the rate for the whole request. This estimate is not a charge cap or a checkout quote. How Credits work.

Exact route: qwen/qwen4-max

Catalog checked 2026-11-17. Model access depends on your plan and current service availability.

Use it in your workspace.

  1. Prepare Qwen Code

    Install Minaco on your Apple silicon Mac, connect your account and prepare the native agent in Agent settings.

  2. Choose the exact model

    Select Qwen Code and a Minaco-credit account mode. If your plan offers Qwen4-Max, choose it from the model selector. Desktop 0.13.14 or later reads the server’s model catalog.

  3. Give it a bounded task

    Open the project folder, provide the necessary context and review any approvals. Inspect the result and usage before expanding the scope.

When the next stage calls for a different agent, finish the turn and switch in the same conversation. Minaco prepares the visible working context for the next native session; hidden reasoning and credentials do not transfer.

How context handoff works →

Read the source.

Qwen model documentation describes the upstream model.

Editorial review: 2026-11-11. Task suggestions and comparisons are Minaco’s guidance, not vendor benchmark results. Minaco is an independent workspace; model API features do not imply that every feature is exposed by the native agent.

Compare nearby choices.

  • Qwen3.8 Max (0902) — Qwen3.8 Max (0902) is the pinned Max version of the Qwen3.8 family published in Minaco.
  • Qwen3.8 Flash — Qwen3.8 Flash is the faster, lower-cost member of the Qwen3.8 family.

Keep the work moving.

Your agents. Your workspace. One place to continue.

Download for Mac